LoadStoreVectorizer crashes due to unsized type

[charukcs]

Summary

When we skip bitcasts while looking for GEP in LoadSoreVectorizer we should also verify that the type is sized otherwise we assert

[rampitec]

Code looks good, please fix the test.

test/CodeGen/X86/loadStore_vectorizer.ll

9 ↗

(On Diff #142712)

Please run the test through opt -instnamer

[charukcs]

Used opt -instnamer on the test file

[rampitec]

LGTM

[charukcs]

I dont have commit privileges can someone please commit this for me. Thanks

llvm/trunk/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp

 
 GetElementPtrInst *Vectorizer::getSourceGEP(Value *Src) const {
   // First strip pointer bitcasts. Make sure pointee size is the same with
   // and without casts.
   // TODO: a stride set by the add instruction below can match the difference
   // in pointee type size here. Currently it will not be vectorized.
   Value *SrcPtr = getLoadStorePointerOperand(Src);
   Value *SrcBase = SrcPtr->stripPointerCasts();
-  if (DL.getTypeStoreSize(SrcPtr->getType()->getPointerElementType()) ==
-      DL.getTypeStoreSize(SrcBase->getType()->getPointerElementType()))
+  Type *SrcPtrType = SrcPtr->getType()->getPointerElementType();
+  Type *SrcBaseType = SrcBase->getType()->getPointerElementType();
+  if (SrcPtrType->isSized() && SrcBaseType->isSized() &&
+      DL.getTypeStoreSize(SrcPtrType) == DL.getTypeStoreSize(SrcBaseType))
     SrcPtr = SrcBase;
   return dyn_cast<GetElementPtrInst>(SrcPtr);
 }
 
 // FIXME: Merge with llvm::isConsecutiveAccess
 bool Vectorizer::isConsecutiveAccess(Value *A, Value *B) {
   Value *PtrA = getLoadStorePointerOperand(A);
   Value *PtrB = getLoadStorePointerOperand(B);

llvm/trunk/test/CodeGen/X86/loadStore_vectorizer.ll

+; RUN: opt -load-store-vectorizer < %s -S | FileCheck %s
+
+%struct_render_pipeline_state = type opaque
+
+define fastcc void @main(%struct_render_pipeline_state addrspace(1)* %pso) unnamed_addr {
+; CHECK: load i16
+; CHECK: load i16
+entry:
+  %tmp = bitcast %struct_render_pipeline_state addrspace(1)* %pso to i16 addrspace(1)*
+  %tmp1 = load i16, i16 addrspace(1)* %tmp, align 2
+  %tmp2 = bitcast %struct_render_pipeline_state addrspace(1)* %pso to i8 addrspace(1)*
+  %sunkaddr51 = getelementptr i8, i8 addrspace(1)* %tmp2, i64 6
+  %tmp3 = bitcast i8 addrspace(1)* %sunkaddr51 to i16 addrspace(1)*
+  %tmp4 = load i16, i16 addrspace(1)* %tmp3, align 2
+  ret void
+}